© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 23185
    Prev
    Next
    INDEX
    Explanations

    wal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arro
    -0.26
    ¶Ī
    -0.25
    lá
    -0.25
    heits
    -0.25
    uali
    -0.24
     identity
    -0.24
    liness
    -0.23
    ugi
    -0.23
     Unterstüt
    -0.23
    å·´å·´
    -0.23
    POSITIVE LOGITS
     Insights
    0.29
    ä½ľä¸ļ
    0.28
    bridge
    0.28
    ero
    0.28
    ç»ĻæĤ¨
    0.27
     Insight
    0.26
    ação
    0.25
     Bold
    0.25
    bel
    0.25
     Ins
    0.25
    Activations Density 0.069%

    No Known Activations